state: generation 11938 (cycle_no_slots)

This commit is contained in:
2026-09-21 23:59:18 +00:00
parent 5e8802451d
commit c4871dfe86
7 changed files with 2113 additions and 2066 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T23:54:31.127689+00:00",
"lastSyncTime": "2026-09-21T23:54:30.855927+00:00",
"generatedAt": "2026-09-21T23:59:03.698072+00:00",
"lastSyncTime": "2026-09-21T23:59:03.362604+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2998,24 +2998,24 @@
"decisionSuccessRate": 0.0625,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 42,
"ambiguous_runtime": 43,
"context_length": 3,
"framework_architecture_unsupported": 26,
"memory_capacity": 1,
"参数/模板问题": 8
},
"failureCount": 80,
"failureRate": 0.9756,
"failureCount": 81,
"failureRate": 0.9759,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0244,
"successRate": 0.0241,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 82,
"unresolvedFailureCount": 50
"total": 83,
"unresolvedFailureCount": 51
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 68,
@@ -3329,23 +3329,23 @@
"decisionSuccessRate": 0.2542,
"decisionTotal": 59,
"failureBreakdown": {
"ambiguous_runtime": 12,
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 31,
"model_load": 11,
"tokenizer_compatibility": 2
},
"failureCount": 56,
"failureRate": 0.7887,
"failureCount": 57,
"failureRate": 0.7917,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 15,
"successRate": 0.2113,
"successRate": 0.2083,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 71,
"unresolvedFailureCount": 12
"total": 72,
"unresolvedFailureCount": 13
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 695,
@@ -5532,7 +5532,7 @@
"decisionSuccessRate": 0.0242,
"decisionTotal": 3635,
"failureBreakdown": {
"ambiguous_runtime": 1500,
"ambiguous_runtime": 1501,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -5546,15 +5546,15 @@
"tokenizer_compatibility": 412,
"参数/模板问题": 46
},
"failureCount": 5958,
"failureCount": 5959,
"failureRate": 0.9854,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 88,
"successRate": 0.0146,
"total": 6046,
"unresolvedFailureCount": 1546
"total": 6047,
"unresolvedFailureCount": 1547
},
"vllm-customized": {
"attributableFailureCount": 6,
@@ -5678,7 +5678,7 @@
"decisionSuccessRate": 0.0482,
"decisionTotal": 83,
"failureBreakdown": {
"ambiguous_runtime": 93,
"ambiguous_runtime": 94,
"backend_operator": 2,
"context_length": 3,
"framework_architecture_unsupported": 66,
@@ -5689,18 +5689,18 @@
"tokenizer_compatibility": 2,
"参数/模板问题": 28
},
"failureCount": 201,
"failureRate": 0.9805,
"failureCount": 202,
"failureRate": 0.9806,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 4,
"successRate": 0.0195,
"total": 205,
"unresolvedFailureCount": 121
"successRate": 0.0194,
"total": 206,
"unresolvedFailureCount": 122
}
},
"generatedAt": "2026-09-21T23:54:31.116699+00:00",
"generatedAt": "2026-09-21T23:59:03.686238+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 99,
@@ -5708,7 +5708,7 @@
"decisionSuccessRate": 0.1681,
"decisionTotal": 119,
"failureBreakdown": {
"ambiguous_runtime": 103,
"ambiguous_runtime": 104,
"context_length": 3,
"framework_architecture_unsupported": 91,
"memory_capacity": 2,
@@ -5718,15 +5718,15 @@
"日志缺失": 3,
"验证失败": 27
},
"failureCount": 271,
"failureRate": 0.9313,
"failureCount": 272,
"failureRate": 0.9315,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 20,
"successRate": 0.0687,
"total": 291,
"unresolvedFailureCount": 172
"successRate": 0.0685,
"total": 292,
"unresolvedFailureCount": 173
},
"Ascend_910-b4": {
"attributableFailureCount": 322,
@@ -5762,7 +5762,7 @@
"decisionSuccessRate": 0.1185,
"decisionTotal": 211,
"failureBreakdown": {
"ambiguous_runtime": 190,
"ambiguous_runtime": 191,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 120,
@@ -5776,15 +5776,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 681,
"failureCount": 682,
"failureRate": 0.9646,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0354,
"total": 706,
"unresolvedFailureCount": 493
"total": 707,
"unresolvedFailureCount": 494
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 717,
@@ -6944,9 +6944,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
"ambiguous_runtime": 5
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "starcoder2",
@@ -6958,8 +6958,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
"total": 5,
"unresolvedFailureCount": 5
},
"Ascend_910-b3|vllm|text-generation|bailing_hybrid|none": {
"attributableFailureCount": 1,
@@ -9244,9 +9244,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "starcoder2",
@@ -9258,8 +9258,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm|text-generation|zaya|none": {
"attributableFailureCount": 1,
@@ -17848,13 +17848,13 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
"ambiguous_runtime": 6
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T18:39:29.750888+00:00",
"lastTerminalAt": "2026-09-21T23:59:03.362578+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -17862,8 +17862,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
"total": 6,
"unresolvedFailureCount": 6
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -18026,16 +18026,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 7,
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 1,
"model_load": 4,
"tokenizer_compatibility": 1
},
"failureCount": 13,
"failureCount": 14,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-21T15:54:37.859021+00:00",
"lastTerminalAt": "2026-09-21T23:59:03.362604+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -18043,8 +18043,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 13,
"unresolvedFailureCount": 7
"total": 14,
"unresolvedFailureCount": 8
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -18622,6 +18622,31 @@
"total": 2,
"unresolvedFailureCount": 2
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-21T23:59:03.362578+00:00",
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -19407,12 +19432,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T00:42:10.765026+00:00",
"lastTerminalAt": "2026-09-21T23:59:03.362604+00:00",
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -19422,8 +19447,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Biren_166m|vllm|text-generation|zaya|none": {
"attributableFailureCount": 1,
@@ -19858,9 +19883,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
"ambiguous_runtime": 3
},
"failureCount": 5,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-21T17:22:47.256939+00:00",
@@ -19873,8 +19898,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
"total": 3,
"unresolvedFailureCount": 3
},
"Cambricon_mlu-370-x8|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
@@ -22858,9 +22883,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 31,
@@ -22873,8 +22898,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
"total": 2,
"unresolvedFailureCount": 2
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|33": {
"attributableFailureCount": 0,
@@ -26413,6 +26438,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|starcoder2|compressed-tensors|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 31,
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|starcoder2|compressed-tensors|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -38740,15 +38789,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16444,
"totalRecords": 16638,
"terminalRecords": 16446,
"totalRecords": 16640,
"totals": {
"attributableFailureCount": 5925,
"decisionFailureRate": 0.8619,
"decisionSuccessRate": 0.1381,
"decisionTotal": 6874,
"failureBreakdown": {
"ambiguous_runtime": 4057,
"ambiguous_runtime": 4059,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 105,
@@ -38764,31 +38813,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15495,
"failureCount": 15497,
"failureRate": 0.9423,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 949,
"successRate": 0.0577,
"total": 16444,
"unresolvedFailureCount": 8645
"total": 16446,
"unresolvedFailureCount": 8647
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Kunlunxin_p-800 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高(≥50%),建议重点关注。",
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -38828,6 +38877,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16638,
"summarizedRecords": 16640,
"version": 1
}